papers

A paper-library command that downloads cited research papers and creates structured summaries in a project's references/papers/ folder.

In plain words
What is it for?
Use it to build a verified reference library for design, experiment, or hypothesis documents, including local digest files and online source links.
Why use it?
It removes the manual work of finding, checking, naming, downloading, and summarising research papers.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/stellarshenson/claude-code-plugins/papers
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00326
Opus 5 $0.00014 $0.00163
Sonnet 5 $0.00006 $0.00065
Haiku 4.5 $0.00003 $0.00033

Measured 2d ago against content hash 71514aa129f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

papers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/datascience/commands/papers.md · 19 lines

What it actually says

Papers

Read the datascience:papers skill first - it is the single source of truth for the artifact naming, the digest format, and the download / verify rules. Do NOT duplicate it here.

What to do

  1. Read the datascience:papers skill
  2. Resolve each paper to a verified open-access PDF URL (prefer arXiv https://arxiv.org/pdf/<id>)
  3. Download into references/papers/[paper] <short name>, <year>.pdf; verify the %PDF magic header - never trust the extension
  4. Write references/papers/[paper digest] <short name>.md using the skill's digest prompt (bold-header title, overview, main findings, key takeaways, tags, source). **Source** MUST be the resolvable online provenance link - never a local filename or path
  5. Cite the digest from the calling document by its local filename; a citation without both artifacts is a defect
  6. Several papers in one round - batch: download all, verify all, digest all, then finalize the citing doc
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 19 lines · 28 tokens per session scan A 71514aa129f6

Subscribe to this mod's changes

papers is a command published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 326 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.